Model techniques map
Techniquessoftware implementationtraining framework

specific method · filed under software implementation

Hugging Face Transformers

The Transformers framework used for model inference, including native inference and CPU-offloaded quantization workflows.

Also called Transformers, HuggingFace Transformers.

sources
4
models
3
labs adopt it
3
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

optional 3used 1

Documented in

Further reading

Picked by hand, not extracted: where to read more, not evidence for anything on this page.

Evidence

4 spans quoted from the sources, strongest treatment first.

We used transformers on a single node with CPU offloading to quantize Ultra layer-by-layer.

usedsoftware implementationin Nemotron 3 UltraNVIDIA

Model-Optimizer’s HuggingFace PTQ script uses transformers native inference

optionalsoftware implementationin Nemotron 3 Ultra

We recommend the following inference frameworks to serve the model: Transformers

optionalsoftware implementationin MiniMax-M3MiniMax

Transformers (v0.5.12+)

optionalsoftware implementationin GLM-5.2Z.ai

Filed alongside

Other methods under software implementation :: training framework.